Intelligent Wavelet Detection System of Fetal ECG Signals Against the Background of Interference

Authors

  • M. O. Khvostivskyi Ternopil Ivan Puluj National Technical University
  • H. I. Franchevska Ternopil Ivan Puluj National Technical University

Keywords:

intelligent system, fetal ECG signal, maternal ECG signal, interference, mathematical model, detection algorithm, wavelet transform, Morlet basis, MATLAB

Abstract

The article considers one of the urgent problems of modern perinatal diagnostics – the detection of the fetal ECG signal against the background of the dominant maternal ECG signal and numerous interferences. The complexity of the problem is due to the significant difference in amplitude levels between the signals (the ratio is more than 3:1 in favor of the mother), their quasi-periodic nature, as well as the presence of various artifacts: myogenic noise, motion interference, and electromagnetic interference. For an adequate description of the processes, a mathematical model of the abdominal ECG recording is proposed, which takes into account the multicomponent nature of the signal mixture, the periodicity of cardiac activity, and the additivity of noise.

Based on the model, intelligent detection system was created, in which the wavelet processing algorithm in the Morlet basis is implemented. This approach allows for multilevel time-frequency analysis, effectively suppressing low-frequency components of the maternal signal, amplifying high-frequency QRS complexes of the fetus, and ensuring noise immunity. The algorithmic support of the system includes a sequence of stages: input of a mixed signal, parameterization of scales and shifts, calculation of wavelet coefficients, construction of 3D and 2D projections of the spectral space, and statistical decision-making regarding the presence of fetal components. Particular attention is paid to the detection of QRS complexes by amplitude-temporal features, which enables to detect regular rhythmic structures even in difficult conditions.

Experimental studies conducted in the MATLAB environment confirmed the effectiveness of the method: the system can reliably distinguish the fetal ECG signal in the frequency range of 2…3 Hz (120…180 beats/min) against the background of the maternal signal with a frequency of 0.8…1.5 Hz (50…90 beats/min). The proposed approach creates the prerequisites for increasing the reliability of non-invasive fetal cardiac monitoring, reduces the risks of diagnostic errors, and can become the basis for intelligent support systems for clinical decisions in real time

Author Biographies

M. O. Khvostivskyi, Ternopil Ivan Puluj National Technical University

Cand. Sc. (Eng.), Associate Professor, Associate Professor of the Chair of Biotechnical Systems

H. I. Franchevska, Ternopil Ivan Puluj National Technical University

Post-Graduate Student, of the Chair of Biotechnical Systems

References

World Health Organization, Newborn mortality. [Online]. Updated Mar. 14, 2024. Available: https://www.who.int. Accessed: Sep. 5, 2025.

B. Widrow, and S. D. Stearns, “Adaptive Signal Processing. Englewood Cliffs,” NJ: Prentice-Hall, p. 491, 1985.

A. Cichocki, and S. Amari, Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications. New York, NY: Wiley, 2002, p. 565. https://doi.org/10.1002/0470845899 .

T.-W. Lee, Independent Component Analysis: Theory and Applications. Boston, MA: Kluwer Academic Publishers, 1998, p. 250. https://doi.org/10.1007/978-1-4757-2851-4 .

В. І. Шульгін, і В. В. Федотенко, «Виділення електрокардіограми плода з багатоканального абдомінального сигналу в реальному масштабі часу,» ІV Міжнародна науково-практична конференція «Інформаційні системи та технології в медицині» (ICM–2021): зб. наук. пр., Харків: Нац. аерокосм. ун-т ім. М. Є. Жуковського «Харків. авіац. ін-т», 2021, с. 122-123. ISBN 978-966-662-842-1.

A. Hyvärinen, Independent Component Analysis. New York, NY: Springer, 2001, p. 495.

P. Comon, “Independent component analysis – a new concept?” Signal Processing, vol. 36, no. 3, pp. 287-314, 1994, https://doi.org/10.1016/0165-1684(94)90029-9 .

J.-F. Cardoso, “Blind signal separation: statistical principles,” Proc. IEEE, vol. 86, no. 10, pp. 2009-2025, 1999.

Т. О. Білобородова, і І. С. Скарга-Бандурова, «Розділення джерел даних і вилучення цільових компонентів електрофізіологічних часових рядів на прикладі ЕКГ плода,» Реєстрація, зберігання і обробка даних, т. 25, с. 43-53, 2023. https://doi.org/10.35681/1560-9189.2023.25.1.287017 .

R. Martinek, et all., “Comparative effectiveness of ICA and PCA in extraction of fetal ECG from abdominal signals: Toward non-invasive fetal monitoring,” Frontiers in Physiology, vol. 9, p. 648, May 30, 2018, https://doi.org/0.3389/fphys.2018.00648.

V. Zarzoso, and A. K. Nandi, “Noninvasive fetal electrocardiogram extraction: Blind separation versus adaptive noise cancellation,” IEEE Trans. Biomed. Eng., vol. 48, no. 1, pp. 12-18, 2001, https://doi.org/10.1109/10.900244 .

R. Sameni, and G. D. Clifford, “A review of fetal ECG signal processing; issues and promising directions,” Open Pacing Electrophysiol. Ther. J., vol. 3, pp. 4-20, 2010, https://doi.org/10.2174/1876536X01003010004 .

М. О. Хвостівський, і Є. Б. Яворська, «Метод виявлення електрокардіосигналу плоду в утробі матері у суміші із завадами,» Вісник Хмельницького національного технологічного університету, № 3, с. 179-184, 2011.

M. Wahbah, et all., “A deep learning framework for noninvasive fetal ECG signal extraction,” Frontiers in Physiology, vol. 15, Apr. 2024, Art. no. 1329313, https://doi.org/10.3389/fphys.2024.1329313 .

L. Chen, S. Wu, and Z. Zhou, “Fetal ECG signal extraction from maternal abdominal ECG signals using Attention R2W-Net,” Sensors, vol. 25, no. 3, p. 601, Jan. 2025, https://doi.org/0.3390/s25030601 .

S. Redif, “Fetal electrocardiogram estimation using polynomial eigenvalue decomposition,” Turkish Journal of Electrical Engineering and Computer Sciences, vol. 24, no. 4, pp. 2483-2497, 2016, https://doi.org/10.3906/elk-1401-19 .

I. V. Yavorskyi, S. V. Uniyat, R. A. Tkachuk, and M. O. Khvostivskyi, “Algorithmic support of wavelet processing of pulse signals in the Morlet basis,” in Mathematics and Mathematical Simulation in a Modern Technical University: Proc. II Int. Sci. Pract. Conf. for Students and Young Scientists, Lutsk, Ukraine, Apr. 30, 2024, pp. 51-53. ISBN 978-966-377-250-9.

Abstract views: 1

Published

2026-02-07

How to Cite

[1]
M. O. Khvostivskyi and H. I. . Franchevska, “Intelligent Wavelet Detection System of Fetal ECG Signals Against the Background of Interference”, Вісник ВПІ, no. 6, pp. 119–126, Feb. 2026.

Issue

No. 6 (2025)

Section

Information technologies and computer sciences

Metrics

Downloads

Download data is not yet available.

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication.
  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).